Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial detail beyond the annotations: a hard cap of 10 results, the returned fields (name, address, rating), that phone numbers are masked, and that it reports the share of sampled listings without a website. The coverage-fallback behavior is also disclosed, which is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what the tool returns and its scope, then appends the use case and fallback in short clauses. Dense with information and no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers scope, output contents and truncation, privacy masking, aggregate metric, and coverage failure handling. With no output schema and fully described parameters, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so field meanings come from the schema. The description still adds the cardinality constraint ("one type in one city"), clarifying that the tool takes a single business_type and city per call rather than lists, which the schema's string types alone do not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource with exact scope: local businesses of one type in one city whose Google Maps listing shows no website. This is clearly distinguishable from the sibling tools (get_local_market_snapshot, list_available_markets), which are broader market-level queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States a concrete use case ("finding businesses that may need a website") and explains the failure path ("When a city or business type is not covered, the result lists what is"), which tells the agent how to recover. It does not explicitly route to a sibling such as list_available_markets for discovering covered markets, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.